© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57181
    Prev
    Next
    INDEX
    Explanations

    looking in directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rée
    -1.25
    ⎼
    -0.98
    bauten
    -0.98
    wendungs
    -0.91
    تيجة
    -0.90
    醯
    -0.89
    rde
    -0.88
    tuje
    -0.88
    lichkeiten
    -0.87
    iren
    -0.86
    POSITIVE LOGITS
     around
    2.53
     down
    1.95
     out
    1.81
     up
    1.71
     across
    1.59
     Around
    1.39
    Around
    1.37
     over
    1.36
    around
    1.34
     into
    1.29
    Activations Density 0.014%

    No Known Activations